DeepMind's Keerthana on Gemini Robotics 2, Cross-Embodiment and Humanoids
The Cognitive Revolution · rss · 2026-10-03
The Cognitive Revolution hosts Keerthana Gopalakrishnan, Research Lead for Gemini Robotics at Google DeepMind, on the release of Gemini Robotics 2 and the path to generalist humanoid robots.
Key points:
- Architecture: pairing reasoning models like Gemini Robotics ER 2 with vision-language-action execution for "one brain, any body"
- Bottlenecks: multi-fingered manipulation and cross-embodiment remain harder problems than bipedal locomotion
- Whole-body humanoid control, progress in robotic hands, and simulation training
- Real-world trade-offs: inference latency, sensor failures, and operational safety where errors carry immediate physical consequences
- The future of robotics data and managing robot fleets
More from Embodied
- ETH's Anymal robot completes 10km autonomous alpine hike with VLM-guided ROAM system — ChongZzZhang · 2026-11-19
- iFixit tears down Apple HomeView: lots of glue and 'endless frustration' — Resident-Fall4351 · 2026-11-19
- Removing human video drops robot OOD success from 60% to 7%: generalization comes from human video — gui_penedo · 2026-11-19
- PSYONIC's prosthetic Ability Hand now used by 90+ robotics orgs, raising Series A — DhowCIO · 2026-11-19
- Simulator misspecification breeds overconfidence: sim-to-real study on SPEED+ — Nikolay Dolgov · 2026-11-19
- Doppel world model renders the robot body and beats action-only baselines across 8 embodiments — mangahomanga · 2026-11-19